Alternatives and similar repositories for koifish

Users that are interested in koifish are comparing it to the libraries listed below

• pierrel55 / llama_st
  Load and run Llama from safetensors files in C
  ☆14Updated last year
• gigit0000 / qwen3.c
  Lightweight C inference for Qwen3 GGUF. Multiturn prefix caching & batch processing.
  ☆19Updated 3 months ago
• jukofyork / transplant-vocab
  Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.
  ☆47Updated last month
• CohleM / lilLM
  A little(lil) Language Model (LM). A tiny reproduction of LLaMA 3's model architecture.
  ☆53Updated 7 months ago
• theroyallab / YALS
  ☆88Updated 2 weeks ago
• pranavjad / tinyllama-bitnet
  Train your own small bitnet model
  ☆76Updated last year
• ngxson / ggml-easy
  Thin wrapper around GGML to make life easier
  ☆40Updated last month
• CerebrasResearch / reap
  REAP: Router-weighted Expert Activation Pruning for SMoE compression
  ☆151Updated 2 weeks ago
• catid / bitnet_cpu
  Experiments with BitNet inference on CPU
  ☆54Updated last year
• adriancable / qwen3.c
  Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.
  ☆150Updated 5 months ago
• reka-ai / rekaquant
  ☆62Updated 5 months ago
• lukasVierling / FaceRWKV
  Course Project for COMP4471 on RWKV
  ☆17Updated last year
• KevlarKanou / rwkv7.c
  Inference RWKV v7 in pure C.
  ☆42Updated 2 months ago
• electroglyph / quant_clone
  Generate a llama-quantize command to copy the quantization parameters of any GGUF
  ☆28Updated 4 months ago
• xTimeCrystal / MiniModel
  ☆38Updated 2 months ago
• janhq / cortex.llamacpp
  cortex.llamacpp is a high-efficiency C++ inference engine for edge computing. It is a dynamic library that can be loaded by any server a…
  ☆41Updated 5 months ago
• rafacelente / bllama
  1.58-bit LLaMa model
  ☆83Updated last year
• RWKV / RWKV-wiki
  RWKV centralised docs for the community
  ☆29Updated 4 months ago
• cahya-wirawan / rwkv-tokenizer
  A fast RWKV Tokenizer written in Rust
  ☆54Updated 4 months ago
• JohannesGaessler / elo_hellm
  ☆16Updated 5 months ago
• mmwillet / TTS.cpp
  TTS support with GGML
  ☆201Updated 2 months ago
• perk11 / large-model-proxy
  Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…
  ☆85Updated last week
• stduhpf / stable-diffusion.cpp
  Stable Diffusion and Flux in pure C/C++
  ☆24Updated this week
• BlinkDL / fast.c
  Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.
  ☆73Updated 10 months ago
• Gryphe / MergeMonster
  An unsupervised model merging algorithm for Transformers-based language models.
  ☆108Updated last year
• kroggen / mamba.c
  Inference of Mamba models in pure C
  ☆195Updated last year
• hscspring / llama.np
  Inference Llama/Llama2/Llama3 Modes in NumPy
  ☆21Updated 2 years ago
• nivibilla / build-nanogpt
  Video+code lecture on building nanoGPT from scratch
  ☆68Updated last year
• balisujohn / tortoise.cpp
  A ggml (C++) re-implementation of tortoise-tts
  ☆193Updated last year
• fishiatee / yawullm
  Yet Another (LLM) Web UI, made with Gemini
  ☆12Updated 11 months ago